AIBullisharXiv – CS AI · 15h ago7/10
🧠
On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
Researchers demonstrate that stochasticity in discrete diffusion models provides an error-correcting mechanism that improves the speed-quality tradeoff in generative AI. They propose Discrete Churn and Restart Sampling (DCRS), which achieves up to 10x faster sampling on images while maintaining quality by strategically injecting controlled randomness into the inference process.